The Power of Medical Imaging for Rare Diseases

Digital Radiography, expert insights, medical imaging, Radiology

Reading Time: 6 minutes read

Diagnostic imaging can be a critical step in treating patients as early as possible.

Sometimes, patients suffering from a rare disease experience a delayed diagnosis. The delay can enable their condition to further advance, possibly jeopardizing their quality of life and, in some cases, life expectancy. By the time the correct diagnosis has been determined, these patients have usually been forced to visit several different doctors, adding to their frustration and uncertainty, and to their loved ones.

To help bring attention to Rare Disease Day (1) on Feb. 28, we are highlighting the success seen with radiology in diagnosing rare diseases and helping patients get treatment as early as possible.

Medical imaging can play an important role in diagnosing rare diseases.

Enhancing diagnostics in diseases of the lung

Although diagnostic scans can sometimes show ambiguous results, a combined technique known as a PET-CT scan has shown success in detecting cardiac sarcoidosis. This is a rare disease that is unpredictable by nature and whose cause is unknown. Nearly 50% of those affected fail to be diagnosed (2) in their lifetime.

Recently, the University of Illinois at Chicago (UIC) developed a new combined PET-CT scan technique that incorporates a 72-hour high-fat, low-sugar diet before images are taken. According to the article in Imaging Technology News, “researchers were able to diagnose cardiac sarcoidosis much more accurately and could diagnose cases that would not have been picked up using the usual 24-hour high-fat, low-sugar protocol normally prescribed before the combined PET-CT scans.” (3) Researchers are now using this technique to study the relationship between cardiac sarcoidosis and sarcoidosis that may have spread to other areas of the body.

Medical imaging also helps to detect other diseases of the lung. Exposure to toxic dust led to a massive influx of industrial workers being diagnosed with rare lung conditions like silicosis and black lung disease. One of the most deadly airborne contaminants still impacting industrial workers to this day is asbestos, a mineral that was heavily used throughout equipment and scattered across worksites. These fibers attribute to nearly 3,000 cases of mesothelioma (4) annually. It is an extremely rare and difficult cancer not only to detect, but also to treat and manage.

Tablet with word Mesothelioma and stethoscope. — *CT is the most common method for detecting malignant pleural mesothelioma.*

Research has found that if a patient has endured long-term exposure to asbestos, radiographic imaging can be effective (5) in assisting doctors with identifying malignant mesothelioma. However, results can point to a number of different diagnoses including adenocarcinomas, lymphoma, and several other chronic lung conditions. This is because chest radiography can detect non-specific abnormalities such as cancerous masses, pleural effusions and pleural thickening, suggestive of mesothelioma only if the patient has a high-risk history.

CT remains the most common method for detecting malignant pleural mesothelioma. However, radiologists might need to combine other techniques like MRI and PET scans in order to interpret the images accurately. Although results may require further research, a study from 2014 (6) concluded that screening high-risk workers could greatly aid in the mortality rate for those exposed to asbestos and should be utilized accordingly.

Looking toward the future of earlier detection

Radiographic efforts have been vital to early detection; however, results may not provide doctors with all the information they need to make the right call. Combining forces with Artificial Intelligence (AI) could help fill this gap by reducing errors and providing radiologists with pre-screened images, saving time for both specialists and patients.

Researchers from Great St. Petersburg Polytechnic University in Russia demonstrated just how powerful the combination could be through an AI software dedicated to lung cancer (7). This intelligence system can not only differentiate between benign and malignant tumors, but also has the uncanny ability to read CT images as quickly as 20 seconds.

Anna Meldo, head of the Radiology Department, explained, “Many different objects may be detected on the CT images, so the main task was to train the system to recognize what each of the objects represents. Using the clinical and radiological classification, we are trying to train the system not only to detect tumors, but to distinguish other diseases similar to cancer.”

This recent study demonstrates just how powerful artificial intelligence can be when combined with radiology, helping critically ill patients perhaps gain an earlier diagnosis. In addition, the nature of AI allows the system to self-improve and with every new CT image that it reads. As a result, it is expected to become more efficient in detecting lung abnormalities.

Although early detection has been a major hurdle for rare diagnoses, diagnostic imaging is playing a critical role in helping patients move into the treatment path sooner.